We propose a flexible probabilistic method for the extraction of earthquake-damaged areas from aerial images. We segment an aerial image into regions and classify each region on the basis of the features appearing in damaged areas. We consider the similarity of neighboring regions in the classification. As a result of segmentation, the classification is independent of the color of each region. Our results show the likelihood of a region being damaged and enable the flexible estimation of damage based on human decisions. The result is displayed on a digital map that can be used for various rescue and humanitarian activities.

Date Published: 25 October 2010
PDF: 10 pages
Proc. SPIE 7831, Earth Resources and Environmental Remote Sensing/GIS Applications, 78311X (25 October 2010); doi: 10.1117/12.864801

Published in SPIE Proceedings Vol. 7831:
Earth Resources and Environmental Remote Sensing/GIS Applications
Ulrich Michel; Daniel L. Civco, Editor(s)